skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Spatially-aware clustering improves AJCC-8 risk stratification performance in oropharyngeal carcinomas
Objective: Evaluate the effectiveness of machine learning tools that incorporate spatial information such as disease location and lymph node metastatic patterns-of-spread, for prediction of survival and toxicity in HPV+ oropharyngeal cancer (OPC). Materials & methods: 675 HPV+ OPC patients that were treated at MD Anderson Cancer Center between 2005 and 2013 with curative intent IMRT were retrospectively collected under IRB approval. Risk stratifications incorporating patient radiometric data and lymph node metastasis patterns via an anatomically-adjacent representation with hierarchical clustering were identified. These clusterings were combined into a 3-level patient stratification and included along with other known clinical features in a Cox model for predicting survival outcomes, and logistic regression for toxicity, using independent subsets for training and validation. Results: Four groups were identified and combined into a 3-level stratification. The inclusion of patient stratifications in predictive models for 5-yr Overall survival (OS), 5-year recurrence free survival, (RFS) and Radiation-associated dysphagia (RAD) consistently improved model performance measured using the area under the curve (AUC). Test set AUC improvements over models with clinical covariates, was 9 % for predicting OS, and 18 % for predicting RFS, and 7 % for predicting RAD. For models with both clinical and AJCC covariates, AUC improvement was 7 %, 9 %, and 2 % for OS, RFS, and RAD, respectively. Conclusion: Including data-driven patient stratifications considerably improve prognosis for survival and toxicity outcomes over the performance achieved by clinical staging and clinical covariates alone. These stratifications generalize well to across cohorts, and sufficient information for reproducing these clusters is included.  more » « less
Award ID(s):
2320261
PAR ID:
10536541
Author(s) / Creator(s):
; ; ; ; ; ; ; ;
Publisher / Repository:
Elsevier ScienceDirect: Oral Oncology
Date Published:
Journal Name:
Oral Oncology
Volume:
144
Issue:
C
ISSN:
1368-8375
Page Range / eLocation ID:
106460
Subject(s) / Keyword(s):
Head & Neck cancer Statistical and research methods Machine learning Radiation oncology Health Informatics Imaging Risk stratification Oropharyngeal cancer Clustering Radiomics
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; ; ; ; ; (, Frontiers in Oncology)
    PURPOSE: Identify Oropharyngeal cancer (OPC) patients at high-risk of developing long-term severe radiation-associated symptoms using dose volume histograms for organs-at-risk, via unsupervised clustering. MATERIAL AND METHODS: All patients were treated using radiation therapy for OPC. Dose-volume histograms of organs-at-risk were extracted from patients’ treatment plans. Symptom ratings were collected via the MD Anderson Symptom Inventory (MDASI) given weekly during, and 6 months post-treatment. Drymouth, trouble swallowing, mucus, and vocal dysfunction were selected for analysis in this study. Patient stratifications were obtained by applying Bayesian Mixture Models with three components to patient’s dose histograms for relevant organs. The clusters with the highest total mean doses were translated into dose thresholds using rule mining. Patient stratifications were compared against Tumor staging information using multivariate likelihood ratio tests. Model performance for prediction of moderate/severe symptoms at 6 months was compared against normal tissue complication probability (NTCP) models using cross-validation. RESULTS: A total of 349 patients were included for long-term symptom prediction. High-risk clusters were significantly correlated with outcomes for severe late drymouth (p <.0001, OR = 2.94), swallow (p = .002, OR = 5.13), mucus (p = .001, OR = 3.18), and voice (p = .009, OR = 8.99). Simplified clusters were also correlated with late severe symptoms for drymouth (p <.001, OR = 2.77), swallow (p = .01, OR = 3.63), mucus (p = .01, OR = 2.37), and voice (p <.001, OR = 19.75). Proposed cluster stratifications show better performance than NTCP models for severe drymouth (AUC.598 vs.559, MCC.143 vs.062), swallow (AUC.631 vs.561, MCC.20 vs -.030), mucus (AUC.596 vs.492, MCC.164 vs -.041), and voice (AUC.681 vs.555, MCC.181 vs -.019). Simplified dose thresholds also show better performance than baseline models for predicting late severe ratings for all symptoms. CONCLUSION: Our results show that leveraging the 3-D dose histograms from radiation therapy plan improves stratification of patients according to their risk of experiencing long-term severe radiation associated symptoms, beyond existing NTPC models. Our rule-based method can approximate our stratifications with minimal loss of accuracy and can proactively identify risk factors for radiation-associated toxicity. 
    more » « less
  2. ; ; ; (, Scientific reports)
    The growing amount of longitudinal data for a large population of patients has necessitated the application of algorithms that can discover patterns that inform patient management. This study demonstrates how temporal patterns generated from a combination of clinical and imaging measurements improve residual survival prediction in glioblastoma patients. Temporal patterns were identified with sequential pattern mining using data from 304 patients. Along with patient covariates, the patterns were incorporated as features in logistic regression models to predict 2-, 6-, or 9-month residual survival at each visit. The modeling approach that included temporal patterns achieved test performances of 0.820, 0.785, and 0.783 area under the receiver operating characteristic curve for predicting 2-, 6-, and 9-month residual survival, respectively. This approach significantly outperformed models that used tumor volume alone (p < 0.001) or tumor volume combined with patient covariates (p < 0.001) in training. Temporal patterns involving an increase in tumor volume above 122 mm3/day, a decrease in KPS across multiple visits, moderate neurologic symptoms, and worsening overall neurologic function suggested lower residual survival. These patterns are readily interpretable and found to be consistent with known prognostic indicators, suggesting they can provide early indicators to clinicians of changes in patient state that inform management decisions. 
    more » « less
  3. ; ; (, Clinical Cancer Research)
    Abstract Introduction: To counteract the rapidly increasing incidence of human papillomavirus (HPV)-related oropharyngeal cancer (OPC), development of effective biomarkers and other novel screening strategies are necessary to effectively detect early disease in well-defined high-risk populations. The most promising biomarkers are circulating tumor HPV DNA (ctHPV), antibodies (Abs) to HPV16 early (E) antigens, and persistent infection with oral oncogenic HPV. Here, we report the prevalence of ctHPV in a population of middle-aged men, a group with high OPC incidence, and evaluate concordance between the three HPV biomarkers. Materials and Methods: We included participants enrolled in the HPV-related Oropharyngeal and Uncommon Cancers Screening Trial of Men (HOUSTON) study between April 2017 and December 2019. The HOUSTON study was designed to evaluate biomarkers and novel screening strategies for HPV-related cancers among middle-aged men (50-64 years), the group with the highest incidence of HPV-related OPC. We tested plasma for ctHPV using a digital droplet polymerase chain reaction (ddPCR) assay (NavDx, Naveris, Waltham, MA). We previously tested the plasma from these participants for HPV16 E Abs using a novel RAPID ELISA and for prevalent oral HPV16 (oHPV16) infection in oral rinse using the cobas HPV Test (Roche Diagnostics, Indianapolis, IN). We used Fisher’s exact test to determine statistical significance for the association between biomarkers (alpha < 0.05). Results: Of 345 samples tested, 343 were adequate for ctHPV analysis. Of these, 314 were negative (92.4%) and two were positive (0.6%; both for HPV16). Twenty-four had an indeterminate (Ind) result (7.0%), meaning ctHPV levels fell outside the established parameters for a negative or positive results. All three markers were available for 340 samples with the following results: ctHPV+/Ab+/oHPV16+: 1 (0.3%); ctHPV+/Ab-/oHPV16-: 1 (0.3%); ctHPV Ind/Ab-/oHPV16+: 3 (0.9%); ctHPV Ind/Ab-/oHPV16-: 21 (6.2%); ctHPV-/Ab+/oHPV16+: 1 (0.3%); ctHPV-/Ab+/oHPV16-: 3 (0.9%); ctHPV-/Ab-/oHPV16+: 16 (4.7%); ctHPV-/Ab-/oHPV16-: 294 (86.5%); all other combinations had no observations. ctHPV was associated with HPV16 E Abs and oHPV16 status individually and combined (individually, p = 0.032 for both and combined, p = 0.025). A ctHPV-/Ab+/oHPV16-man was diagnosed with an anal low-grade squamous intraepithelial lesion and was persistently high-risk HPV-positive at the right tonsil/base of tongue. One man was positive for all three markers and was subsequently diagnosed with stage II (T1N1) HPV16-positive/Epstein-Barr-negative nasopharyngeal cancer four months following study enrollment. Conclusions: ctHPV was rare in a general population of middle-aged men. Our results suggest that these markers in combination may be able to correctly identify early HPV-related cancers. Larger studies are needed to confirm this finding. The authors accept sole responsibility for the statements in this abstract. Citation Format: Kristina R. Dahlstrom, Karen S. Anderson, Erich M. Sturgis. Biomarkers for early diagnosis of human papillomavirus-related oropharyngeal cancer [abstract]. In: Proceedings of the AACR-AHNS Head and Neck Cancer Conference: Innovating through Basic, Clinical, and Translational Research; 2023 Jul 7-8; Montreal, QC, Canada. Philadelphia (PA): AACR; Clin Cancer Res 2023;29(18_Suppl):Abstract nr PO-037. 
    more » « less
  4. ; ; ; ; ; ; ; ; (, Cancer Gene Therapy)
    null (Ed.)
    Abstract Thus far immunotherapy has had limited impact on ovarian cancer. Vigil (a novel DNA-based multifunctional immune-therapeutic) has shown clinical benefit to prolong relapse-free survival (RFS) and overall survival (OS) in the BRCA wild type and HRP populations. We further analyzed molecular signals related to sensitivity of Vigil treatment. Tissue from patients enrolled in the randomized double-blind trial of Vigil vs. placebo as maintenance in frontline management of advanced resectable ovarian cancer underwent DNA polymorphism analysis. Data was generated from a 981 gene panel to determine the tumor mutation burden and classify variants using Ingenuity Variant Analysis software (Qiagen) or NIH ClinVar. Only variants classified as pathogenic or likely pathogenic were included. STRING application (version 1.5.1) was used to create a protein-protein interaction network. Topological distance and probability of co-mutation were used to calculated the C-score and cumulative C-score (cumC-score). Kaplan–Meier analysis was used to determine the relationship between gene pairs with a high cumC-score and clinical parameters. Improved relapse free survival in Vigil treated patients was found for the TP53 m- BRCA wt-HRP group compared to placebo (21.1 months versus 5.6 months p  = 0.0013). Analysis of tumor mutation burden did not reveal statistical benefit in patients receiving Vigil versus placebo. Results suggest a subset of ovarian cancer patients with enhanced susceptibility to Vigil immunotherapy. The hypothesis-generating data presented invites a validation study of Vigil in target identified populations, and supports clinical consideration of STRING-generated network application to biomarker characterization with other cancer patients targeted with Vigil. 
    more » « less
  5. ; ; ; ; ; ; ; ; (, Briefings in Bioinformatics)
    Abstract Cancer is an umbrella term that includes a wide spectrum of disease severity, from those that are malignant, metastatic, and aggressive to benign lesions with very low potential for progression or death. The ability to prognosticate patient outcomes would facilitate management of various malignancies: patients whose cancer is likely to advance quickly would receive necessary treatment that is commensurate with the predicted biology of the disease. Former prognostic models based on clinical variables (age, gender, cancer stage, tumor grade, etc.), though helpful, cannot account for genetic differences, molecular etiology, tumor heterogeneity, and important host biological mechanisms. Therefore, recent prognostic models have shifted toward the integration of complementary information available in both molecular data and clinical variables to better predict patient outcomes: vital status (overall survival), metastasis (metastasis-free survival), and recurrence (progression-free survival). In this article, we review 20 survival prediction approaches that integrate multi-omics and clinical data to predict patient outcomes. We discuss their strategies for modeling survival time (continuous and discrete), the incorporation of molecular measurements and clinical variables into risk models (clinical and multi-omics data), how to cope with censored patient records, the effectiveness of data integration techniques, prediction methodologies, model validation, and assessment metrics. The goal is to inform life scientists of available resources, and to provide a complete review of important building blocks in survival prediction. At the same time, we thoroughly describe the pros and cons of each methodology, and discuss in depth the outstanding challenges that need to be addressed in future method development. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email